Related papers: TS-URGENet: A Three-stage Universal Robust and Gen…
Text-to-speech synthesis (TTS) has witnessed rapid progress in recent years, where neural methods became capable of producing audios with high naturalness. However, these efforts still suffer from two types of latencies: (a) the {\em…
Recent progress in diffusion-based audio generation and restoration has substantially improved performance across heterogeneous conditioning regimes, including text-conditioned audio generation and audio-conditioned super-resolution.…
Speech enhancement methods based on deep learning have surpassed traditional methods. While many of these new approaches are operating on the wideband (16kHz) sample rate, a new fullband (48kHz) speech enhancement system is proposed in this…
Real-world audio recordings often contain multiple speakers and various degradations, which limit both the quantity and quality of speech data available for building state-of-the-art speech processing models. Although end-to-end approaches…
Speech super-resolution (SSR) enhances low-resolution speech by increasing the sampling rate. While most SSR methods focus on magnitude reconstruction, recent research highlights the importance of phase reconstruction for improved…
This paper proposes MP-SENet, a novel Speech Enhancement Network which directly denoises Magnitude and Phase spectra in parallel. The proposed MP-SENet adopts a codec architecture in which the encoder and decoder are bridged by…
Streaming speech enhancement is a crucial task for real-time applications such as online meetings, smart home appliances, and hearing aids. Deep neural network-based approaches achieve exceptional performance while demanding substantial…
The ultimate goal of expressive speech-to-speech translation (S2ST) is to accurately translate spoken content while preserving the speaker identity and emotional style. However, progress in this field is largely hindered by three key…
This paper presents a novel streaming end-to-end target-speaker speech recognition that addresses two critical limitations in systems: the handling of noisy enrollment utterances and specific enrollment phrase requirements. This paper…
We propose Uni-ArrayDPS, a novel diffusion-based refinement framework for unified multi-channel speech enhancement and separation. Existing methods for multi-channel speech enhancement/separation are mostly discriminative and are highly…
We introduce SupertonicTTS, a novel text-to-speech (TTS) system designed for efficient and streamlined speech synthesis. SupertonicTTS comprises three components: a speech autoencoder for continuous latent representation, a text-to-latent…
Dysarthric speech exhibits high variability and limited labeled data, posing major challenges for both automatic speech recognition (ASR) and assistive speech technologies. Existing approaches rely on synthetic data augmentation or speech…
This work introduces UDPNet, a novel architecture designed to accelerate the reverse diffusion process in speech synthesis. Unlike traditional diffusion models that rely on timestep embeddings and shared network parameters, UDPNet unrolls…
We propose an end-to-end joint optimization framework of a multi-channel neural speech extraction and deep acoustic model without mel-filterbank (FBANK) extraction for overlapped speech recognition. First, based on a multi-channel…
Recent advances in the design of neural network architectures, in particular those specialized in modeling sequences, have provided significant improvements in speech separation performance. In this work, we propose to use a bio-inspired…
Speech is essential for human communication, yet millions of people face impairments such as dysarthria, stuttering, and aphasia conditions that often lead to social isolation and reduced participation. Despite recent progress in automatic…
Extracting the speech of a target speaker from mixed audios, based on a reference speech from the target speaker, is a challenging yet powerful technology in speech processing. Recent studies of speaker-independent speech separation, such…
Text-to-speech (TTS) systems offer the opportunity to compensate for a hearing loss at the source rather than correcting for it at the receiving end. This removes limitations such as time constraints for algorithms that amplify a sound in a…
Complex-valued processing has brought deep learning-based speech enhancement and signal extraction to a new level. Typically, the process is based on a time-frequency (TF) mask which is applied to a noisy spectrogram, while complex masks…
In this work, we exploit speech enhancement for improving a recurrent neural network transducer (RNN-T) based ASR system. We employ a dense convolutional recurrent network (DCRN) for complex spectral mapping based speech enhancement, and…